-
Notifications
You must be signed in to change notification settings - Fork 66
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
no open Cam detection #65
Comments
Thanks for the feedback. |
same issue |
Thanks for the feedback. I don't see any error message from the log, and wonder whether it works with single image input. |
Yes, " run_jpeg.bat " can get result without problem |
OK. So it would be either the camera or the decoder issue. You may try to input with a video file like: %cd%..\bin\camera_yolov8_nx1x4 -c 5 -x 1 -y 1 -s video/test.mp4 -D If it works, it would be the camera issue, otherwise it will be the decoder. |
(ryzenai) C:\Users\AM5\Desktop\AMD_IPU\RyzenAI-SW\tutorial\yolov8_e2e\bin>camera_yolov8_nx1x4.exe -c 5 -x 1 -y 1 -s WIN_20240425_01_54_05_Pro.mp4 -D nothing happened |
It could be a video encode/decode issue then. Thanks for the feedback, I will get back to you as soon as I can. |
Do you see the same problem when running the multi-model demo below? |
Yes, i can run multi-model demo normally |
Interesting. You mean it runs well with video input? |
Yes,and i try replace multi-model-exec\ipu_modulesx4_demo\resource\detection.avi with other video file, it can also run by "run_modelx4.bat",but if i use the "detection.avi" to run camera_yolov8_nx1x4.exe -c 5 -x 1 -y 1 -s detection.avi -D, it still nothing. |
Thanks for the feedback. Which laptop you are currently using? |
i use desktop system,CPU:R7 8700G |
I believe the root cause is the glog and gflags are not properly found, although those files are provided in the repo. git clone https://github.com/gflags/gflags.git cd ../.. git clone https://github.com/google/glog.git |
When install glog ,I get some error as blow (ryzenai) C:\Users\AM5\Desktop\AMD_IPU>git clone https://github.com/google/glog.git (ryzenai) C:\Users\AM5\Desktop\AMD_IPU>cd glog (ryzenai) C:\Users\AM5\Desktop\AMD_IPU\glog>mkdir mybuild (ryzenai) C:\Users\AM5\Desktop\AMD_IPU\glog>cd mybuild (ryzenai) C:\Users\AM5\Desktop\AMD_IPU\glog\mybuild>cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DCMAKE_CONFIGURATION_TYPES=Release -A x64 -T host=x64 -G "Visual Studio 16 2019" '-DCMAKE_INSTALL_PREFIX=C:\Program Files\glog' '-DCMAKE_PREFIX_PATH=.\glog' -DCMAKE_BUILD_TYPE=Release -DBUILD_opencv_python2=OFF -DBUILD_opencv_python3=OFF -DBUILD_WITH_STATIC_CRT=OFF -B build -S ../ "C:/Users/AM5/Desktop/AMD_IPU/glog/mybuild/'-DCMAKE_INSTALL_PREFIX=C:/Program" CMake Warning: "'-DCMAKE_PREFIX_PATH=.\glog'" -- Selecting Windows SDK version 10.0.19041.0 to target Windows 10.0.22631.
-- Build files have been written to: C:/Users/AM5/Desktop/AMD_IPU/glog/mybuild/build (ryzenai) C:\Users\AM5\Desktop\AMD_IPU\glog\mybuild>cmake --build build --config Release 1>Checking Build System (ryzenai) C:\Users\AM5\Desktop\AMD_IPU\glog\mybuild>cmake --install build --config Release |
I can't reproduce this issue. Maybe you can try to follow the instructions on https://github.com/google/glog to install the glog. |
Updates to NPU-GPU example to use environment variables
I installed the SW but when tried to use ./camera.bat cant open the cam detection:
(yolo) PS C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement> .\camera.bat
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>set XLNX_VART_FIRMWARE=C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement..\1x4.xclbin
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>set VITISAI_EP_JSON_CONFIG=C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement..\vaip_config.json
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>set ENV_PATH=C:\Users\Lenovo\anaconda3\envs\yolo
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>set PATH=C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement..\lib;C:\Users\Lenovo\anaconda3\envs\yolo;C:\Users\Lenovo\anaconda3\envs\yolo;C:\Users\Lenovo\anaconda3\envs\yolo\Library\mingw-w64\bin;C:\Users\Lenovo\anaconda3\envs\yolo\Library\usr\bin;C:\Users\Lenovo\anaconda3\envs\yolo\Library\bin;C:\Users\Lenovo\anaconda3\envs\yolo\Scripts;C:\Users\Lenovo\anaconda3\envs\yolo\bin;C:\Users\Lenovo\anaconda3\condabin;C:\Windows\System32\AMD;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Users\Lenovo\AppData\Local\Microsoft\WindowsApps;C:\Program Files\CMake\bin;C:\Program Files\PowerShell\7;C:\Program Files\Git\cmd;C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Scripts;C:\Users\Lenovo\AppData\Local\Programs\Python\Python312;C:\Users\Lenovo\anaconda3;C:\Users\Lenovo\anaconda3\Library\mingw-w64\bin;C:\Users\Lenovo\anaconda3\Library\usr\bin;C:\Users\Lenovo\anaconda3\Library\bin;C:\Users\Lenovo\anaconda3\Scripts
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>set PATHONHOME=C:\Users\Lenovo\anaconda3\envs\yolo
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>set PYTHONPATH=C:\Users\Lenovo\anaconda3\envs\yolo\Lib;C:\Users\Lenovo\anaconda3\envs\yolo\DLLs
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>set NUM_OF_DPU_RUNNERS=4
C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement..\bin\camera_yolov8_nx1x4 -c 5 -x 1 -y 1 -s 0 -D -R 1920x1080 -r 2560x1440
WARNING: Logging before InitGoogleLogging() is written to STDERR
I20240406 03:18:53.926563 5636 demo_nx1x4.hpp:544] Setting parallelism to 5
I20240406 03:18:53.926563 5636 demo_nx1x4.hpp:548] Setting intra_op_num_threads to 1
I20240406 03:18:53.926563 5636 demo_nx1x4.hpp:552] Setting inter_op_num_threads to 1
I20240406 03:18:53.926563 5636 demo_nx1x4.hpp:575] stream: 0
I20240406 03:18:53.926563 5636 demo_nx1x4.hpp:557] [Disable thread spinning]
I20240406 03:18:53.942196 5636 demo_nx1x4.hpp:582] [Set camera resolution]: 1920x1080
I20240406 03:18:53.942196 5636 demo_nx1x4.hpp:588] [Set display resolution]: 2560x1440
Setting intra_op_num_threads to 1
Setting inter_op_num_threads to 1
Disabling intra-op thread spinning entirely
2024-04-06 03:18:56.8644029 [W:onnxruntime:DetectionModel_int.onnx, vitisai_provider_factory.cc:48 onnxruntime::VitisAIProviderFactory::CreateProvider] Construting a FlexML EP instance in Vitis AI EP
2024-04-06 03:18:56.8903007 [W:onnxruntime:DetectionModel_int.onnx, vitisai_execution_provider.cc:117 onnxruntime::VitisAIExecutionProvider::SetFlexMLEPPtr] Assigning the FlexML EP pointer in Vitis AI EP
2024-04-06 03:18:57.1089813 [W:onnxruntime:DetectionModel_int.onnx, vitisai_execution_provider.cc:137 onnxruntime::VitisAIExecutionProvider::GetCapability] Trying FlexML EP GetCapability
2024-04-06 03:18:57.1114426 [W:onnxruntime:DetectionModel_int.onnx, flexml_execution_provider.cc:180 onnxruntime::FlexMLExecutionProvider::GetCapability] FlexMLExecutionProvider::GetCapability, C:\amd\voe\binary-modules\ResNet.flexml\flexml_bm.signature can't not be found!
2024-04-06 03:18:57.1151299 [W:onnxruntime:DetectionModel_int.onnx, vitisai_execution_provider.cc:153 onnxruntime::VitisAIExecutionProvider::GetCapability] FlexML EP ignoring a non-ResNet50 graph
WARNING: Logging before InitGoogleLogging() is written to STDERR
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:346] Vitis AI EP Load ONNX Model Success
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:347] Graph Input Node Name/Shape (1)
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:351] DetectionModel::input_0 : [-1x3x640x640]
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:357] Graph Output Node Name/Shape (4)
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:361] 3604 : [1x84x8400]
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:361] 3152 : [-1x144x80x80]
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:361] 3341 : [-1x144x40x40]
I20240406 03:18:57.165781 5636 vitisai_compile_model.cpp:361] 3530 : [-1x144x20x20]
[Vitis AI EP] No. of Operators : CPU 55 IPU 1237 95.74%
[Vitis AI EP] No. of Subgraphs :Actually running on IPU 1
2024-04-06 03:18:57.4651225 [W:onnxruntime:, session_state.cc:1169 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2024-04-06 03:18:57.5085635 [W:onnxruntime:, session_state.cc:1171 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
W20240406 03:18:57.652791 5636 tool_function.cpp:171] The operator named 3531, type: :Shape, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.652791 5636 tool_function.cpp:171] The operator named 3533, type: :Gather, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.652791 5636 tool_function.cpp:171] The operator named 3536, type: :Unsqueeze, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.652791 5636 tool_function.cpp:171] The operator named 3539, type: :Concat, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3540_pre_q, type: :Reshape, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3540_q_to_dq, type: :QuantizeLinear, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3540_post_dq, type: :DequantizeLinear, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named :3562:3563, type: :Split, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3562, type: Selector, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3603, type: :Sigmoid, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3578, type: :Transpose, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3579, type: :Softmax, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3582, type: :Conv, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3594, type: :Add, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3592, type: :Sub, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3598, type: :Div, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
W20240406 03:18:57.668411 5636 tool_function.cpp:171] The operator named 3602, type: :Mul, is not defined in XIR. XIR creates the definition of this operator automatically. You should specify the shape and the data_type of the output tensor of this operation by set_attr("shape", std::vector) and set_attr("data_type", std::string)
I20240406 03:18:58.392455 5636 demo_nx1x4.hpp:383] DPU model size=640x640
(yolo) PS C:\Users\Lenovo\Desktop\Yolo\RyzenAI-SW\tutorial\yolov8_e2e\implement>
The text was updated successfully, but these errors were encountered: